Author: Tom Likens
Date: 19:09:10 01/16/03
Go up one level in this thread
On January 16, 2003 at 13:31:39, David Rasmussen wrote: >I do more or less the same thing as everybody else, when probing EGTB's, judging >from the open source programs I've inspected. But I get a severe drop in NPS >when the tables are probed heavily. Much more than other programs, from what I >can see on ICC. > >What could be the course of this? >I have the same order of number of probes as other programs as I can see on ICC. >So my limiting of probes is not the problem. I only probe in the first couple of >plys and if there have just been a change of material on the board. The harddisk >I use is very fast. It is a Western Digital 80GB 7200 RPM with 8MB cache. So >that shouldn't be the problem either. I use NTFS, not FAT, I don't know if that >makes a difference, or file systems in general. I haven't done any serious >testing of this on EXT2, EXT3, ReiserFS etc. But as far as I know, people are >able to do this on Windows, so I must be able to do it too. > >If you have any ideas on how to test or narrow down what's wrong, please post. > >/David David, I had this same problem initially and (as Dieter suggested) commenting out the 4-1 tablebase define helped tremendously. Also increasint the default cache size to 8M gave me another boost. Before I sped it up, I would see an order of magnitude slow down when probing the tablebases :( If you compile using the Intel compiler and use its profile guided optimizations, you might want to ensure that the TB code is enabled for your profile gathering runs. Currently, I see about a 3-4x slow down when I start hitting the tablebases (I use an IDE drive similar to the one you described). regards, --tom
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.